INSPECTr Project

Project Resources

We are pleased to make available various INSPECTr project resources that provide essential, easy-to-access information on the INSPECTr project and its activities. These resources provide a concise overview of the project’s main objectives, goals, and technical innovations.

Project Video

Project Results

18 deliverables in the INSPECTr project are classified for public dissemination.
The remaining 62 deliverables are classified as confidential; i.e., only for members of the consortium (including the Commission Services).

Each of the public deliverables will be reviewed for dissemination to the public and will be hosted on the project website, if deemed appropriate when complete.

Deliverable No.	Title	Month	Availability
D1.5	INSPECTr evaluation and policy recommendations	Feb 2023	Pending Review
D2.1	Initial Legislative compliance relating to law-enforcement powers and evidence requirements	May 2021	Approved
D2.2	Legislative compliance relating to law-enforcement powers and evidence requirements	Feb 2023	Pending Review
D2.3	Reference Digital Forensics Domain Model	May 2021	Approved
D2.4	e-Codex infrastructure evaluation in the context of deployment in LLs	May 2021	Approved
D2.5	Reference Framework for Standardization of Evidence Representation and Exchange	Feb 2023	Pending Review
D6.6	Dissemination – Period 1	Feb 2021	Approved
D6.7	Dissemination – Period 2	Feb 2022	Pending Review
D6.8	Dissemination – Period 3	Feb 2023	Pending Review
D8.1	INSPECTr Research ethics and data protection	Feb 2020	Approved
D8.2	First Report on Ethical Governance	Feb 2021	Approved
D8.3	Second Report on Ethical Governance	Aug 2021	Pending Review
D8.4	Third Report on Ethical Governance	Feb 2023	Pending Review
D8.5	Ethical, Legal and Social requirements for the INSPECTr platform and tools	Feb 2021	Approved
D8.6	Ethical, Legal and Social requirements for the INSPECTr platform and tools – Final Report	Feb 2023	Pending Review
D8.7	Privacy and Ethics-by-design in the INSPECTr platform.	Aug 2021	Pending Review
D8.8	Guide on privacy and ethics-by-design in law enforcement technology	Feb 2023	Pending Review
D8.9	Report on FOSS Compliance	Feb 2023	Pending Review

Academic Publications

Title

Iterative Learning for Semi-automatic Annotation Using User Feedback

Abstract

With the advent of state-of-the-art models based on Neural Networks, the need for vast corpora of accurately labelled data has become fundamental. However, building such datasets is a very resource-consuming task that additionally requires domain expertise.

The present work seeks to alleviate this limitation by proposing an interactive semi-automatic annotation tool using an incremental learning approach to reduce human effort. The automatic models used to assist the annotation are incrementally improved based on user corrections to better annotate the next data.

To demonstrate the effectiveness of the proposed method, we build a dataset with named entities and relations between them related to the crime field with the help of the tool. Analysis results show that annotation effort is considerably reduced while still maintaining the annotation quality compared to fully manual labelling.

Authors:

Meryem Guemimi, Daniel Camara
Center for Data Science, Judiciary Pôle of the French Gendarmerie,Pontoise, France

Ray Genoe
Centre for Cybersecurity and Cybercrime Investigation, University College Dublin, Dublin, Ireland

Publication:
The proceedings of the 4th International Conference on Intelligent Technologies and Applications
(INTAP 2021)
View

Title

LEA Capacity Building as a Driver for the Adoption of European Research

Abstract

The INSPECTr project aims to produce a proof of concept that will demonstrate solutions to many of the issues faced by institutional procedures within law enforcement agencies (LEAs) for combating cybercrime. Unlike many other H2020 projects, the results of INSPECTr will be freely available to stakeholders at the end of the project, despite having a low technology readiness level. It is imperative that LEAs fully understand the legal, security and ethical requirements for using disruptive and advanced technologies, particularly with a platform that will provide AI assisted decision making, facilitate intelligence gathering from online data sources and redefine how evidential data is discovered in other jurisdictions and exchanged. However, INSPECTr will also require the support of stakeholders beyond the scope of the project, in order to drive further development and investment towards market-readiness. The development of a robust capacity building program has been included in the project to ensure that LEAs can confidently use the system and that they fully understand both the pitfalls and the potential of the platform.

During our training needs analyses, various European instruments, standards and priorities are considered, such as CEPOL’s EU Strategic Training Needs Assessment, the course development standards established by ECTEG and Europol’s Training Competency Framework. With this research and through consultation with internal and external stakeholders, we define the pathways of training for the INSPECTr platform in which we aim to address the various roles in European LEAs and their requirements for the effective delivery and assessment of the course. In keeping with the project’s ethics-by-design approach, the training program produced by INSPECTr will have a strong emphasis on security and the fundamental rights of citizens while addressing the gaps in capabilities and training within the EU LEA community. In this paper we describe the process we apply to curriculum design, based on the findings of our research and our continued engagement with LEA and technical partners throughout the life-cycle of the project.

Authors:

Michael Whelan, Ray Genoe
Centre for Cybersecurity and Cybercrime Investigation, University College Dublin, Ireland

Publication:
The proceedings of the CEPOL Research & Science Conference 2022,
Vilnius, Lithuania
View

Title

Developing of a Judicial Cases Cross-Check system for case searching and correlation using a standard for the Evidence.

Abstract

In a recent EU publication, a report commissioned by the European Union related to the Cross-border Digital Criminal Justice environment, a set of specific business needs have been identified. Some of the most relevant ones have been: i) the interoperability across different systems needs to be ensured, ii) the stakeholders need to easily manage the data and ensure its quality, allowing them to properly make use of it (e.g. use the data as evidence in a given case) and iii) the stakeholders investigating a given case should be able to identify links between cross-border cases. Therefore, solutions are needed to allow the stakeholder to search and find relevant information they need for the case they are handling. The article presents a set of solutions to address the highlighted needs, including a ‘Judicial Cases Cross-Check System’. Such a system should provide a tool being able to search for case-related information and identify links among cases that are being investigated in other EU Member States or by Justice and Home Affairs (JHA) agencies and EU bodies. To facilitate the development of the above solution, a standard representation of the metadata and data of the evidence should be adopted. In particular the Unified Cyber Ontology (UCO) and Cyber-investigation Analysis Standard Expression (CASE), dedicated to the digital forensic domain, seem the most promising one to this aim. Moreover, it provides a structured specification for representing information that are analysed and exchanged during investigations involving digital evidence.

Authors:

Gerardo Giardiello, Fabrizio Turchi
Institute of Legal Informatics and Judicial Systems, National Research Council of Italy (CNR-IGSG)

Publication:
The proceedings of the CEPOL Research & Science Conference 2022,
Vilnius, Lithuania
View

Title

Classification of Complaints for Criminal Intelligence Purposes

Abstract

The increase in the volume of available data is changing how people perceive their own fields and how the people may interact with this surplus of information. Public security is not different; Law Enforcement Agencies (LEAs) now have available a large quantity of information to help them fight criminality. One challenging problem is to classify/predict criminal activities. The differentiation over two different complaints may only be clear through the careful analysis of complaints' open text fields, e.g., the modus operandi, where it is described the specificity of the perpetrated crime. Sometimes the intention behind a crime is not evident unless it is correlated to other crimes and patterns get extracted from them. This chapter shows that it is possible to classify criminal data using machine learning-based methods and that open text fields, such as the modus operandi, may play a fundamental role in the performance of the classification.

Authors:

Pauline Rousseau, Dimitris Kotzinos
CY Cergy Paris University, France

Daniel Camara
Center for Data Science, Judiciary Pôle of the French Gendarmerie, Pontoise, France

Publication:
Book chapter in Applied Artificial Intelligence and Robotics for Government Processes
View